English
Related papers

Related papers: Infinite Width Limits of Self Supervised Neural Ne…

200 papers

Given the complexity of genetic risk prediction, there is a critical need for the development of novel methodologies that can effectively capture intricate genotype--phenotype relationships (e.g., nonlinear) while remaining statistically…

Applications · Statistics 2025-10-03 Heng Ge , Qing Lu

We present a simple picture of the training process of joint embedding self-supervised learning methods. We find that these methods learn their high-dimensional embeddings one dimension at a time in a sequence of discrete, well-separated…

Machine Learning · Computer Science 2023-05-31 James B. Simon , Maksis Knutins , Liu Ziyin , Daniel Geisz , Abraham J. Fetterman , Joshua Albrecht

This paper aims to discuss the impact of random initialization of neural networks in the neural tangent kernel (NTK) theory, which is ignored by most recent works in the NTK theory. It is well known that as the network's width tends to…

Machine Learning · Statistics 2024-10-10 Guhan Chen , Yicheng Li , Qian Lin

Previous influential work showed that infinite width limits of neural networks in the lazy training regime are described by kernel machines. Here, we show that neural networks trained in the rich, feature learning infinite-width regime in…

Machine Learning · Computer Science 2025-09-12 Clarissa Lauditi , Blake Bordelon , Cengiz Pehlevan

Deep Neural Networks miss a principled model of their operation. A novel framework for supervised learning based on Topological Quantum Field Theory that looks particularly well suited for implementation on quantum processors has been…

The infinite width limit of random neural networks is known to result in Neural Networks as Gaussian Process (NNGP) (Lee et al. (2018)), characterized by task-independent kernels. It is widely accepted that larger network widths contribute…

Machine Learning · Computer Science 2025-03-11 Zechen Zhang , Haim Sompolinsky

We establish explicit dynamics for neural networks whose training objective has a regularising term that constrains the parameters to remain close to their initial value. This keeps the network in a lazy training regime, where the dynamics…

Machine Learning · Statistics 2023-12-21 Eugenio Clerico , Benjamin Guedj

In this article, we review the literature on statistical theories of neural networks from three perspectives: approximation, training dynamics and generative models. In the first part, results on excess risks for neural networks are…

Machine Learning · Statistics 2024-09-17 Namjoon Suh , Guang Cheng

Infinite width limit has shed light on generalization and optimization aspects of deep learning by establishing connections between neural networks and kernel methods. Despite their importance, the utility of these kernel methods was…

Machine Learning · Computer Science 2022-09-12 Insu Han , Amir Zandieh , Jaehoon Lee , Roman Novak , Lechao Xiao , Amin Karbasi

Contemporary deep neural networks exhibit impressive results on practical problems. These networks generalize well although their inherent capacity may extend significantly beyond the number of training examples. We analyze this behavior in…

Machine Learning · Computer Science 2015-09-03 Tamir Hazan , Tommi Jaakkola

For small training set sizes $P$, the generalization error of wide neural networks is well-approximated by the error of an infinite width neural network (NN), either in the kernel or mean-field/feature-learning regime. However, after a…

Machine Learning · Statistics 2022-12-26 Alexander Atanasov , Blake Bordelon , Sabarish Sainathan , Cengiz Pehlevan

Recent works have partly attributed the generalization ability of over-parameterized neural networks to frequency bias -- networks trained with gradient descent on data drawn from a uniform distribution find a low frequency fit before high…

Machine Learning · Computer Science 2020-03-11 Ronen Basri , Meirav Galun , Amnon Geifman , David Jacobs , Yoni Kasten , Shira Kritchman

Finite-width one hidden layer networks with multiple neurons in the readout layer display non-trivial output-output correlations that vanish in the lazy-training infinite-width limit. In this manuscript we leverage recent progress in the…

Disordered Systems and Neural Networks · Physics 2024-12-23 P. Baglioni , L. Giambagli , A. Vezzani , R. Burioni , P. Rotondo , R. Pacelli

We analyze the convergence of the averaged stochastic gradient descent for overparameterized two-layer neural networks for regression problems. It was recently found that a neural tangent kernel (NTK) plays an important role in showing the…

Machine Learning · Statistics 2021-06-14 Atsushi Nitanda , Taiji Suzuki

This paper studies the infinite-width limit of deep linear neural networks initialized with random parameters. We obtain that, when the number of neurons diverges, the training dynamics converge (in a precise sense) to the dynamics obtained…

Machine Learning · Computer Science 2022-12-01 Lénaïc Chizat , Maria Colombo , Xavier Fernández-Real , Alessio Figalli

We consider optimizing two-layer neural networks in the mean-field regime where the learning dynamics of network weights can be approximated by the evolution in the space of probability measures over the weight parameters associated with…

Machine Learning · Computer Science 2022-10-19 Jingwei Zhang , Xunpeng Huang , Jincheng Yu

Convergence of deep neural networks as the depth of the networks tends to infinity is fundamental in building the mathematical foundation for deep learning. In a previous study, we investigated this question for deep ReLU networks with a…

Machine Learning · Computer Science 2022-01-25 Yuesheng Xu , Haizhang Zhang

Recent work has argued that neural networks can be understood theoretically by taking the number of channels to infinity, at which point the outputs become Gaussian process (GP) distributed. However, we note that infinite Bayesian neural…

Machine Learning · Statistics 2020-06-25 Laurence Aitchison

By leveraging the kernel trick in the output space, kernel-induced losses provide a principled way to define structured output prediction tasks for a wide variety of output modalities. In particular, they have been successfully used in the…

Machine Learning · Statistics 2024-06-14 Tamim El Ahmad , Junjie Yang , Pierre Laforgue , Florence d'Alché-Buc

In practical situations, the tree ensemble is one of the most popular models along with neural networks. A soft tree is a variant of a decision tree. Instead of using a greedy method for searching splitting rules, the soft tree is trained…

Machine Learning · Computer Science 2022-03-22 Ryuichi Kanoh , Mahito Sugiyama